feat: complete repo explainer agent with eval harness and optimizer#1
Merged
Conversation
…and result dataclass
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this PR delivers
A complete agentic AI system built on the Claude Agent SDK that reads
any codebase and answers natural language questions about it.
Three pillars
🤖 Agent — Multi-step agentic loop with 5 filesystem tools. Reads
files, searches code, maps dependencies, synthesizes grounded answers.
Supports both local paths and GitHub URLs transparently.
📊 Eval Harness — 8 test cases with 4 weighted metrics (topic
coverage, hallucination penalty, answer length, groundedness).
Saves full JSON reports per run.
⚡ Optimizer — Automated prompt tuning loop. Runs evals, identifies
failures, asks Claude to improve the system prompt, keeps improvements
and reverts regressions.
Results
Infrastructure
dev